{"data":[{"id":"deepseek/deepseek-v4.1-flash-1017","canonical_slug":"deepseek/deepseek-v4.1-flash-20261017","hugging_face_id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","created":1792225624,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000003","overrides":[{"utc_days":["saturday","sunday"],"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000003"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":0,"utc_end":100,"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000003"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":100,"utc_end":400,"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.000000006"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":400,"utc_end":600,"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000003"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":600,"utc_end":1000,"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.000000006"},{"utc_days":["monday","tuesday","wednesday","thursday","friday"],"utc_start":1000,"utc_end":0,"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000003"}]},"top_provider":{"context_length":1048576,"max_completion_tokens":393216,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4.1-flash-20261017/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"spreadsheet","elo":1265,"win_rate":47.8,"rank":9},{"arena":"models","category":"3d","elo":1337,"win_rate":47.9,"rank":14},{"arena":"models","category":"asciiart","elo":1221,"win_rate":48,"rank":22},{"arena":"models","category":"codecategories","elo":1279,"win_rate":48.4,"rank":21},{"arena":"models","category":"dataviz","elo":1270,"win_rate":51.5,"rank":29},{"arena":"models","category":"gamedev","elo":1248,"win_rate":43.4,"rank":34},{"arena":"models","category":"svg","elo":1234,"win_rate":50.5,"rank":21},{"arena":"models","category":"uicomponent","elo":1278,"win_rate":48.3,"rank":28},{"arena":"models","category":"website","elo":1290,"win_rate":51.6,"rank":20}],"artificial_analysis":{"intelligence_index":32.6,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":42.2,"strategy_and_ops_index":49.2,"legal_index":37.7,"healthcare_and_medical_index":41.3,"engineering_index":37.6,"economics_index":38.5,"cyber_index":56.8,"openness_index":44.4,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"}},{"id":"tencent/hy4-flash","canonical_slug":"tencent/hy4-flash-20261116","hugging_face_id":"tencent/Hy4-flash","name":"Tencent: Hy4 flash","created":1794838706,"description":"Hy4 flash is a cost-efficient variant of [Hy4](https://orr.api.report.finance/tencent/hy4) from Tencent, served with roughly a quarter of the flagship's parameter count for lower latency and cost. It targets code assistance, agent...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000035","completion":"0.0000001405","input_cache_read":"0.0000000015"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/tencent/hy4-flash-20261116/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1221,"win_rate":46.3,"rank":41},{"arena":"models","category":"codecategories","elo":1227,"win_rate":45,"rank":50},{"arena":"models","category":"gamedev","elo":1212,"win_rate":43.5,"rank":49},{"arena":"models","category":"uicomponent","elo":1269,"win_rate":48.1,"rank":33},{"arena":"models","category":"website","elo":1228,"win_rate":44.6,"rank":57}]},"reasoning":{"mandatory":false,"default_enabled":true}},{"id":"deepseek/deepseek-v4.1-flash","canonical_slug":"deepseek/deepseek-v4.1-flash-20260910","hugging_face_id":"deepseek-ai/DeepSeek-V4.1-Flash","name":"DeepSeek: DeepSeek V4.1 Flash","created":1789021285,"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.000000006"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4.1-flash-20260910/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":null,"strategy_and_ops_index":null,"legal_index":null,"healthcare_and_medical_index":null,"engineering_index":null,"economics_index":null,"cyber_index":40.8,"openness_index":44.4,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"}},{"id":"z-ai/glm-5.3-flash","canonical_slug":"z-ai/glm-5.3-flash-20260826","hugging_face_id":"zai-org/GLM-5.3-Flash","name":"Z.ai: GLM 5.3 Flash","created":1787752741,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000015","completion":"0.0000005","input_cache_read":"0.00000003"},"top_provider":{"context_length":1048575,"max_completion_tokens":943717,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-5.3-flash-20260826/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"pdf","elo":1136,"win_rate":38.1,"rank":32},{"arena":"models","category":"3d","elo":1286,"win_rate":54.9,"rank":21},{"arena":"models","category":"asciiart","elo":1255,"win_rate":53.5,"rank":15},{"arena":"models","category":"codecategories","elo":1259,"win_rate":48.3,"rank":30},{"arena":"models","category":"dataviz","elo":1256,"win_rate":50.1,"rank":35},{"arena":"models","category":"gamedev","elo":1260,"win_rate":46.5,"rank":29},{"arena":"models","category":"svg","elo":1266,"win_rate":54.8,"rank":16},{"arena":"models","category":"uicomponent","elo":1293,"win_rate":51.9,"rank":21},{"arena":"models","category":"website","elo":1253,"win_rate":47.2,"rank":41}],"artificial_analysis":{"intelligence_index":27.8,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":38.8,"strategy_and_ops_index":44.5,"legal_index":34.8,"healthcare_and_medical_index":36.6,"engineering_index":34.5,"economics_index":35.3,"cyber_index":49.9,"openness_index":44.4,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"}},{"id":"stepfun/step-5-preview","canonical_slug":"stepfun/step-5-preview-20261008","hugging_face_id":"stepfun-ai/Step-5-Preview","name":"StepFun: Step 5 Preview","created":1791462849,"description":"Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000001","completion":"0.0000027","input_cache_read":"0.0000001"},"top_provider":{"context_length":1000000,"max_completion_tokens":64000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/stepfun/step-5-preview-20261008/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":28.5,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":40.5,"strategy_and_ops_index":44.2,"legal_index":38.6,"healthcare_and_medical_index":39.9,"engineering_index":37,"economics_index":38.6,"cyber_index":47.7,"openness_index":33.3,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}},{"id":"meta/muse-spark-1.3-contributor","canonical_slug":"meta/muse-spark-1.3-contributor-20260902","hugging_face_id":null,"name":"Meta: Muse Spark 1.3 Contributor","created":1788381519,"description":"Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information...","context_length":1048576,"architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000002","web_search":"0.0025","input_cache_read":"0.000000002"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/meta/muse-spark-1.3-contributor-20260902/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low","minimal"],"default_effort":"medium"}},{"id":"xiaomi/mimo-v2.6-flash","canonical_slug":"xiaomi/mimo-v2.6-flash-20260921","hugging_face_id":"XiaomiMiMo/MiMo-V2.6-Flash-RL","name":"Xiaomi: MiMo-V2.6-Flash","created":1790021264,"description":"MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...","context_length":1050000,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","image","video","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000014","completion":"0.00000028","input_cache_read":"0.0000000028"},"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"frequency_penalty":0},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/xiaomi/mimo-v2.6-flash-20260921/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":26.7,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":36.9,"strategy_and_ops_index":45.7,"legal_index":33.8,"healthcare_and_medical_index":35.1,"engineering_index":31,"economics_index":32.2,"cyber_index":null,"openness_index":52.8,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false}},{"id":"openai/gpt-6-luna","canonical_slug":"openai/gpt-6-luna-20260922","hugging_face_id":null,"name":"OpenAI: GPT-6 Luna","created":1790100786,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000005","web_search":"0.01","input_cache_read":"0.00000001","input_cache_write":"0.000000125","overrides":[{"min_prompt_tokens":272000,"prompt":"0.0000002","completion":"0.00000075","input_cache_read":"0.00000002","input_cache_write":"0.00000025"}]},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-6-luna-20260922/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":27.9,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":33.9,"strategy_and_ops_index":43.2,"legal_index":32.2,"healthcare_and_medical_index":34.8,"engineering_index":33.3,"economics_index":34.5,"cyber_index":52.7,"openness_index":null,"multilingual_index":null,"decision_index":75.7}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"}},{"id":"moonshotai/kimi-k3.1-pro","canonical_slug":"moonshotai/kimi-k3.1-pro-20261023","hugging_face_id":"moonshotai/Kimi-K3.1-Pro","name":"MoonshotAI: Kimi K3.1 Pro","created":1792778188,"description":"Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000253","completion":"0.0000088","input_cache_read":"0.00000018"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"top_p":0.95},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/moonshotai/kimi-k3.1-pro-20261023/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1162,"win_rate":44.3,"rank":25},{"arena":"agents","category":"codetovideo","elo":1242,"win_rate":59.5,"rank":8},{"arena":"agents","category":"fullstack","elo":1322,"win_rate":62,"rank":3},{"arena":"agents","category":"mobileapps","elo":1267,"win_rate":59.4,"rank":5},{"arena":"agents","category":"pdf","elo":1226,"win_rate":55.9,"rank":14},{"arena":"agents","category":"python-pptxslides","elo":1287,"win_rate":60.3,"rank":3},{"arena":"agents","category":"spreadsheet","elo":1318,"win_rate":62.6,"rank":4},{"arena":"agents","category":"webapps","elo":1302,"win_rate":60.4,"rank":3},{"arena":"models","category":"3d","elo":1437,"win_rate":70.4,"rank":3},{"arena":"models","category":"asciiart","elo":1300,"win_rate":57.9,"rank":8},{"arena":"models","category":"codecategories","elo":1342,"win_rate":60.4,"rank":7},{"arena":"models","category":"dataviz","elo":1293,"win_rate":55.1,"rank":15},{"arena":"models","category":"gamedev","elo":1395,"win_rate":65.6,"rank":4},{"arena":"models","category":"svg","elo":1321,"win_rate":61.9,"rank":4},{"arena":"models","category":"uicomponent","elo":1384,"win_rate":65.1,"rank":1},{"arena":"models","category":"website","elo":1317,"win_rate":57.4,"rank":8}],"artificial_analysis":{"intelligence_index":46.5,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":53.3,"strategy_and_ops_index":57.6,"legal_index":49.2,"healthcare_and_medical_index":51.6,"engineering_index":50.9,"economics_index":49.9,"cyber_index":64.1,"openness_index":33.3,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"max"}},{"id":"anthropic/claude-opus-5.5","canonical_slug":"anthropic/claude-opus-5.5-20260921","hugging_face_id":null,"name":"Anthropic: Claude Opus 5.5","created":1790094732,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.000004","completion":"0.00002","web_search":"0.01","input_cache_read":"0.0000002","input_cache_write":"0.000005","input_cache_write_1h":"0.000008"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-opus-5.5-20260921/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1393,"win_rate":74.5,"rank":1},{"arena":"agents","category":"blender3d","elo":1222,"win_rate":57.6,"rank":4},{"arena":"agents","category":"codetovideo","elo":1343,"win_rate":72.9,"rank":2},{"arena":"agents","category":"fullstack","elo":1383,"win_rate":70.2,"rank":2},{"arena":"agents","category":"mobileapps","elo":1295,"win_rate":62,"rank":3},{"arena":"agents","category":"pdf","elo":1312,"win_rate":68.1,"rank":3},{"arena":"agents","category":"spreadsheet","elo":1292,"win_rate":53.3,"rank":6},{"arena":"agents","category":"webapps","elo":1316,"win_rate":62.6,"rank":2},{"arena":"models","category":"3d","elo":1454,"win_rate":65.2,"rank":2},{"arena":"models","category":"asciiart","elo":1349,"win_rate":64.8,"rank":3},{"arena":"models","category":"codecategories","elo":1377,"win_rate":60.9,"rank":2},{"arena":"models","category":"dataviz","elo":1385,"win_rate":63.9,"rank":1},{"arena":"models","category":"gamedev","elo":1420,"win_rate":63.8,"rank":1},{"arena":"models","category":"svg","elo":1315,"win_rate":54,"rank":5},{"arena":"models","category":"uicomponent","elo":1372,"win_rate":62.7,"rank":4},{"arena":"models","category":"website","elo":1322,"win_rate":55.5,"rank":7}],"artificial_analysis":{"intelligence_index":59.1,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":59.4,"strategy_and_ops_index":61.4,"legal_index":58,"healthcare_and_medical_index":57.9,"engineering_index":65.3,"economics_index":60.3,"cyber_index":28.7,"openness_index":null,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"}},{"id":"z-ai/glm-5.3","canonical_slug":"z-ai/glm-5.3-20260816","hugging_face_id":"zai-org/GLM-5.3","name":"Z.ai: GLM 5.3","created":1787086655,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000000699","completion":"0.0000014","input_cache_read":"0.0000000689"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-5.3-20260816/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1285,"win_rate":55.3,"rank":22},{"arena":"models","category":"asciiart","elo":1180,"win_rate":44.7,"rank":30},{"arena":"models","category":"codecategories","elo":1274,"win_rate":52.1,"rank":23},{"arena":"models","category":"dataviz","elo":1248,"win_rate":50.4,"rank":36},{"arena":"models","category":"gamedev","elo":1279,"win_rate":50.3,"rank":23},{"arena":"models","category":"svg","elo":1239,"win_rate":51,"rank":20},{"arena":"models","category":"uicomponent","elo":1282,"win_rate":53.1,"rank":25},{"arena":"models","category":"website","elo":1275,"win_rate":52.4,"rank":25},{"arena":"agents","category":"htmlslides","elo":1189,"win_rate":39.1,"rank":2},{"arena":"agents","category":"mobileapps","elo":1184,"win_rate":52.2,"rank":25},{"arena":"agents","category":"python-pptxslides","elo":1217,"win_rate":47.6,"rank":10},{"arena":"agents","category":"webapps","elo":1270,"win_rate":54.2,"rank":10}],"artificial_analysis":{"intelligence_index":31.7,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":42.1,"strategy_and_ops_index":47.4,"legal_index":35.8,"healthcare_and_medical_index":39.3,"engineering_index":37.6,"economics_index":37.3,"cyber_index":36.4,"openness_index":33.3,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"}},{"id":"tencent/hy4","canonical_slug":"tencent/hy4-20261104","hugging_face_id":"tencent/Hy4","name":"Tencent: Hy4","created":1793766031,"description":"The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000417","completion":"0.0000012505","input_cache_read":"0.000000021"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/tencent/hy4-20261104/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"pdf","elo":1260,"win_rate":58.3,"rank":8},{"arena":"models","category":"3d","elo":1240,"win_rate":46.3,"rank":31},{"arena":"models","category":"codecategories","elo":1248,"win_rate":47.5,"rank":41},{"arena":"models","category":"gamedev","elo":1272,"win_rate":50.3,"rank":26},{"arena":"models","category":"uicomponent","elo":1184,"win_rate":38,"rank":71},{"arena":"models","category":"website","elo":1250,"win_rate":47.6,"rank":43}],"artificial_analysis":{"intelligence_index":34.6,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":38,"strategy_and_ops_index":48.7,"legal_index":35.4,"healthcare_and_medical_index":42.9,"engineering_index":41.1,"economics_index":38.3,"cyber_index":58,"openness_index":null,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","low","none"],"default_effort":"high"}},{"id":"minimax/minimax-m3.1-flash","canonical_slug":"minimax/minimax-m3.1-flash-20261019","hugging_face_id":"MiniMaxAI/MiniMax-M3.1-Flash","name":"MiniMax: MiniMax M3.1 Flash","created":1792379569,"description":"MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000075","completion":"0.0000003","input_cache_read":"0.0000000075","overrides":[{"utc_start":1500,"utc_end":100,"prompt":"0.000000075","completion":"0.0000003","input_cache_read":"0.0000000075"},{"utc_start":100,"utc_end":1500,"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000015"}]},"top_provider":{"context_length":1048576,"max_completion_tokens":524288,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/minimax/minimax-m3.1-flash-20261019/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[],"artificial_analysis":{"intelligence_index":29.1,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":39.1,"strategy_and_ops_index":50.8,"legal_index":33,"healthcare_and_medical_index":36.8,"engineering_index":34.3,"economics_index":37.4,"cyber_index":null,"openness_index":27.8,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"max"}},{"id":"openai/gpt-6.1-sol","canonical_slug":"openai/gpt-6.1-sol-20260929","hugging_face_id":null,"name":"OpenAI: GPT-6.1 Sol","created":1790702882,"description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.00001","web_search":"0.01","input_cache_read":"0.0000001","input_cache_write":"0.0000025","overrides":[{"min_prompt_tokens":272000,"prompt":"0.000004","completion":"0.000015","input_cache_read":"0.0000002","input_cache_write":"0.000005"}]},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-6.1-sol-20260929/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1193,"win_rate":49.5,"rank":15},{"arena":"agents","category":"blender3d","elo":1239,"win_rate":60.6,"rank":2},{"arena":"agents","category":"codetovideo","elo":1193,"win_rate":54.9,"rank":13},{"arena":"agents","category":"mobileapps","elo":1227,"win_rate":52.9,"rank":13},{"arena":"agents","category":"pdf","elo":1126,"win_rate":41.5,"rank":36},{"arena":"agents","category":"spreadsheet","elo":1209,"win_rate":41.3,"rank":14},{"arena":"agents","category":"webapps","elo":1283,"win_rate":57.2,"rank":7},{"arena":"models","category":"3d","elo":1419,"win_rate":59.1,"rank":5},{"arena":"models","category":"codecategories","elo":1355,"win_rate":57,"rank":4},{"arena":"models","category":"dataviz","elo":1280,"win_rate":52.6,"rank":18},{"arena":"models","category":"gamedev","elo":1400,"win_rate":60,"rank":3},{"arena":"models","category":"svg","elo":1336,"win_rate":60.2,"rank":3},{"arena":"models","category":"uicomponent","elo":1356,"win_rate":58.8,"rank":6},{"arena":"models","category":"website","elo":1313,"win_rate":54.1,"rank":10}],"artificial_analysis":{"intelligence_index":54.6,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":56.2,"strategy_and_ops_index":57.6,"legal_index":53.7,"healthcare_and_medical_index":52,"engineering_index":59.4,"economics_index":56.3,"cyber_index":null,"openness_index":null,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"}},{"id":"z-ai/glm-5.2","canonical_slug":"z-ai/glm-5.2-20260616","hugging_face_id":"zai-org/GLM-5.2","name":"Z.ai: GLM 5.2","created":1781631930,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000062","completion":"0.00000242","input_cache_read":"0.00000014"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":1,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-5.2-20260616/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1156,"win_rate":49.7,"rank":9},{"arena":"agents","category":"androidnative","elo":1170,"win_rate":52.8,"rank":23},{"arena":"agents","category":"blender3d","elo":983,"win_rate":36.1,"rank":21},{"arena":"agents","category":"fullstack","elo":1211,"win_rate":60,"rank":15},{"arena":"agents","category":"godotgamedev","elo":1142,"win_rate":40.1,"rank":20},{"arena":"agents","category":"htmlslides","elo":1073,"win_rate":49.5,"rank":15},{"arena":"agents","category":"mobileapps","elo":1154,"win_rate":47.6,"rank":31},{"arena":"agents","category":"pdf","elo":1256,"win_rate":59.9,"rank":9},{"arena":"agents","category":"python-pptxslides","elo":1160,"win_rate":48.4,"rank":18},{"arena":"agents","category":"spreadsheet","elo":1013,"win_rate":41,"rank":25},{"arena":"agents","category":"webapps","elo":1201,"win_rate":55.6,"rank":20},{"arena":"models","category":"3d","elo":1258,"win_rate":52.7,"rank":26},{"arena":"models","category":"asciiart","elo":1173,"win_rate":46.3,"rank":33},{"arena":"models","category":"codecategories","elo":1268,"win_rate":50.5,"rank":28},{"arena":"models","category":"dataviz","elo":1280,"win_rate":51.7,"rank":17},{"arena":"models","category":"gamedev","elo":1248,"win_rate":49,"rank":35},{"arena":"models","category":"svg","elo":1190,"win_rate":47.1,"rank":32},{"arena":"models","category":"uicomponent","elo":1282,"win_rate":55.1,"rank":26},{"arena":"models","category":"website","elo":1273,"win_rate":49.8,"rank":28}],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":32.1,"strategy_and_ops_index":30,"legal_index":28.5,"healthcare_and_medical_index":28.7,"engineering_index":null,"economics_index":32.1,"cyber_index":null,"openness_index":44.4,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","high","none"],"default_effort":"high"}},{"id":"anthropic/claude-sonnet-5.5","canonical_slug":"anthropic/claude-sonnet-5.5-20260928","hugging_face_id":null,"name":"Anthropic: Claude Sonnet 5.5","created":1790618686,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.00001","web_search":"0.01","input_cache_read":"0.0000001","input_cache_write":"0.0000025","input_cache_write_1h":"0.000004"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anthropic/claude-sonnet-5.5-20260928/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1265,"win_rate":58.8,"rank":6},{"arena":"agents","category":"blender3d","elo":1233,"win_rate":59.8,"rank":3},{"arena":"agents","category":"codetovideo","elo":1320,"win_rate":70.2,"rank":3},{"arena":"agents","category":"mobileapps","elo":1257,"win_rate":57.4,"rank":6},{"arena":"agents","category":"pdf","elo":1249,"win_rate":58.8,"rank":12},{"arena":"agents","category":"spreadsheet","elo":1251,"win_rate":46.1,"rank":10},{"arena":"agents","category":"webapps","elo":1296,"win_rate":58.8,"rank":4},{"arena":"models","category":"3d","elo":1396,"win_rate":55.7,"rank":8},{"arena":"models","category":"codecategories","elo":1337,"win_rate":55.7,"rank":9},{"arena":"models","category":"dataviz","elo":1358,"win_rate":64.3,"rank":3},{"arena":"models","category":"gamedev","elo":1377,"win_rate":58.3,"rank":6},{"arena":"models","category":"svg","elo":1292,"win_rate":55.4,"rank":9},{"arena":"models","category":"uicomponent","elo":1383,"win_rate":63.3,"rank":2},{"arena":"models","category":"website","elo":1305,"win_rate":53.2,"rank":14}],"artificial_analysis":{"intelligence_index":54.5,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":55.8,"strategy_and_ops_index":58.1,"legal_index":52.2,"healthcare_and_medical_index":54.2,"engineering_index":58.5,"economics_index":54.1,"cyber_index":null,"openness_index":null,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"}},{"id":"deepseek/deepseek-v4-flash-0731","canonical_slug":"deepseek/deepseek-v4-flash-20260731","hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","created":1785478908,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":"0.000000062","completion":"0.0000003","input_cache_read":"0.000000035"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"default_parameters":{},"supported_voices":[],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-flash-20260731/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1180,"win_rate":48.8,"rank":57},{"arena":"models","category":"asciiart","elo":1081,"win_rate":34,"rank":66},{"arena":"models","category":"codecategories","elo":1211,"win_rate":46.5,"rank":61},{"arena":"models","category":"dataviz","elo":1168,"win_rate":40,"rank":73},{"arena":"models","category":"gamedev","elo":1191,"win_rate":44.8,"rank":61},{"arena":"models","category":"svg","elo":1165,"win_rate":44.7,"rank":44},{"arena":"models","category":"uicomponent","elo":1224,"win_rate":47.1,"rank":53},{"arena":"models","category":"website","elo":1227,"win_rate":46.8,"rank":59}],"artificial_analysis":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":null,"strategy_and_ops_index":null,"legal_index":null,"healthcare_and_medical_index":null,"engineering_index":null,"economics_index":null,"cyber_index":null,"openness_index":44.4,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"}},{"id":"moonshotai/kimi-k3","canonical_slug":"moonshotai/kimi-k3-20260715","hugging_face_id":"moonshotai/Kimi-K3","name":"MoonshotAI: Kimi K3","created":1784215858,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000000192","completion":"0.000016","input_cache_read":"0.000000182"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":0.95,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/moonshotai/kimi-k3-20260715/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1202,"win_rate":54,"rank":4},{"arena":"agents","category":"androidnative","elo":1253,"win_rate":57,"rank":7},{"arena":"agents","category":"blender3d","elo":1120,"win_rate":40.4,"rank":9},{"arena":"agents","category":"codetovideo","elo":1278,"win_rate":63.4,"rank":4},{"arena":"agents","category":"fullstack","elo":1285,"win_rate":61.1,"rank":5},{"arena":"agents","category":"godotgamedev","elo":1199,"win_rate":48.7,"rank":13},{"arena":"agents","category":"htmlslides","elo":1155,"win_rate":55.6,"rank":5},{"arena":"agents","category":"mobileapps","elo":1253,"win_rate":56.5,"rank":9},{"arena":"agents","category":"pdf","elo":1276,"win_rate":64.7,"rank":5},{"arena":"agents","category":"python-pptxslides","elo":1223,"win_rate":53.9,"rank":9},{"arena":"agents","category":"spreadsheet","elo":1054,"win_rate":27.9,"rank":19},{"arena":"agents","category":"webapps","elo":1275,"win_rate":58,"rank":9},{"arena":"models","category":"3d","elo":1358,"win_rate":63.7,"rank":12},{"arena":"models","category":"asciiart","elo":1351,"win_rate":68.3,"rank":2},{"arena":"models","category":"codecategories","elo":1345,"win_rate":60.4,"rank":5},{"arena":"models","category":"dataviz","elo":1349,"win_rate":63.6,"rank":4},{"arena":"models","category":"gamedev","elo":1349,"win_rate":55.4,"rank":9},{"arena":"models","category":"svg","elo":1294,"win_rate":59.7,"rank":8},{"arena":"models","category":"uicomponent","elo":1335,"win_rate":60.2,"rank":11},{"arena":"models","category":"website","elo":1335,"win_rate":59.5,"rank":4}],"artificial_analysis":{"intelligence_index":17.4,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":28.3,"strategy_and_ops_index":37,"legal_index":27.7,"healthcare_and_medical_index":29.2,"engineering_index":22.8,"economics_index":27.7,"cyber_index":41.3,"openness_index":38.9,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"max"}},{"id":"meta/muse-ember","canonical_slug":"meta/muse-ember-20261109","hugging_face_id":null,"name":"Meta: Muse Ember","created":1794247648,"description":"Muse Ember is the smallest and most efficient model from Meta that’s designed for complex reasoning execution and the work agents repeat all day: tool calls, coding agent subtasks, routing,...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000001","completion":"0.0000005","web_search":"0.0025","input_cache_read":"0.000000004","input_cache_write":"0.000000125"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/meta/muse-ember-20261109/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1362,"win_rate":61.5,"rank":11},{"arena":"models","category":"codecategories","elo":1339,"win_rate":60.7,"rank":8},{"arena":"models","category":"dataviz","elo":1315,"win_rate":60.1,"rank":12},{"arena":"models","category":"gamedev","elo":1324,"win_rate":59.5,"rank":14},{"arena":"models","category":"uicomponent","elo":1308,"win_rate":55.8,"rank":16},{"arena":"models","category":"website","elo":1327,"win_rate":59.5,"rank":6}],"artificial_analysis":{"intelligence_index":36,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":44.6,"strategy_and_ops_index":48.7,"legal_index":38.5,"healthcare_and_medical_index":41.3,"engineering_index":41.8,"economics_index":41,"cyber_index":null,"openness_index":null,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low","minimal"],"default_effort":"max"}},{"id":"google/gemini-4-carbon","canonical_slug":"google/gemini-4-carbon-20261110","hugging_face_id":null,"name":"Google: Gemini 4 Carbon","created":1794326871,"description":"Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work. It takes text, image, audio, video and file input, supports long decode...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0.00001","image":"0.000002","audio":"0.000002","input_audio_cache":"0.0000001","web_search":"0.014","internal_reasoning":"0.00001","input_cache_read":"0.0000001","input_cache_write":"0.0000001875"},"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-4-carbon-20261110/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses"],"benchmarks":{"design_arena":[{"arena":"agents","category":"codetovideo","elo":1275,"win_rate":62.5,"rank":5},{"arena":"agents","category":"mobileapps","elo":1294,"win_rate":62.2,"rank":4},{"arena":"agents","category":"pdf","elo":1309,"win_rate":67.1,"rank":4},{"arena":"agents","category":"spreadsheet","elo":1224,"win_rate":48.9,"rank":13},{"arena":"models","category":"3d","elo":1416,"win_rate":68.3,"rank":6},{"arena":"models","category":"codecategories","elo":1333,"win_rate":58.7,"rank":11},{"arena":"models","category":"dataviz","elo":1334,"win_rate":60.6,"rank":8},{"arena":"models","category":"gamedev","elo":1327,"win_rate":57.6,"rank":12},{"arena":"models","category":"svg","elo":1394,"win_rate":68.9,"rank":1},{"arena":"models","category":"uicomponent","elo":1347,"win_rate":59.7,"rank":8},{"arena":"models","category":"website","elo":1306,"win_rate":55,"rank":12}],"artificial_analysis":{"intelligence_index":60,"coding_index":null,"agentic_index":null,"finance_and_accounting_index":62.6,"strategy_and_ops_index":60.9,"legal_index":62,"healthcare_and_medical_index":56.8,"engineering_index":65.3,"economics_index":59.6,"cyber_index":null,"openness_index":null,"multilingual_index":null,"decision_index":null}},"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"}}],"total_count":20,"links":{"next":null}}